J3's picture
First Push
e3c1489
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.6342987418174744,
"min": 0.611826479434967,
"max": 2.8895530700683594,
"count": 100
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 6028.375,
"min": 5859.5888671875,
"max": 29859.4921875,
"count": 100
},
"SnowballTarget.Step.mean": {
"value": 999952.0,
"min": 9952.0,
"max": 999952.0,
"count": 100
},
"SnowballTarget.Step.sum": {
"value": 999952.0,
"min": 9952.0,
"max": 999952.0,
"count": 100
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
"value": 26.869827270507812,
"min": 0.4533454179763794,
"max": 26.895301818847656,
"count": 100
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 5239.6162109375,
"min": 87.94901275634766,
"max": 5486.6416015625,
"count": 100
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 100
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 8756.0,
"min": 8756.0,
"max": 10945.0,
"count": 100
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.023210509348427874,
"min": 0.013451722073659767,
"max": 0.025281097720144318,
"count": 100
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.0928420373937115,
"min": 0.05380688829463907,
"max": 0.1264054886007216,
"count": 100
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.20799658447504044,
"min": 0.12345400713384153,
"max": 0.42968487322330473,
"count": 100
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8319863379001617,
"min": 0.4938160285353661,
"max": 2.1484243661165237,
"count": 100
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 4.58899541200001e-07,
"min": 4.58899541200001e-07,
"max": 9.945880054120002e-05,
"count": 100
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 1.835598164800004e-06,
"min": 1.835598164800004e-06,
"max": 0.000492344007656,
"count": 100
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.10045880000000001,
"min": 0.10045880000000001,
"max": 0.19945880000000005,
"count": 100
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.40183520000000006,
"min": 0.40183520000000006,
"max": 0.992344,
"count": 100
},
"SnowballTarget.Policy.Beta.mean": {
"value": 3.289412000000004e-05,
"min": 3.289412000000004e-05,
"max": 0.004972994119999999,
"count": 100
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.00013157648000000017,
"min": 0.00013157648000000017,
"max": 0.024617965600000007,
"count": 100
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 25.866666666666667,
"min": 2.8863636363636362,
"max": 26.654545454545456,
"count": 100
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1164.0,
"min": 127.0,
"max": 1466.0,
"count": 100
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.866666666666667,
"min": 2.8863636363636362,
"max": 26.654545454545456,
"count": 100
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1164.0,
"min": 127.0,
"max": 1466.0,
"count": 100
},
"SnowballTarget.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 100
},
"SnowballTarget.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 100
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1679033630",
"python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \n[GCC 9.4.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics",
"mlagents_version": "0.31.0.dev0",
"mlagents_envs_version": "0.31.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.11.0+cu102",
"numpy_version": "1.21.2",
"end_time_seconds": "1679035864"
},
"total": 2234.6664284109997,
"count": 1,
"self": 0.4318077259999882,
"children": {
"run_training.setup": {
"total": 0.10434466499998507,
"count": 1,
"self": 0.10434466499998507
},
"TrainerController.start_learning": {
"total": 2234.1302760199997,
"count": 1,
"self": 2.640317158011385,
"children": {
"TrainerController._reset_env": {
"total": 9.682192443999952,
"count": 1,
"self": 9.682192443999952
},
"TrainerController.advance": {
"total": 2221.6816182549883,
"count": 90937,
"self": 1.3171824209948682,
"children": {
"env_step": {
"total": 2220.3644358339934,
"count": 90937,
"self": 1504.9415722369615,
"children": {
"SubprocessEnvManager._take_step": {
"total": 714.072904704984,
"count": 90937,
"self": 11.4195488749981,
"children": {
"TorchPolicy.evaluate": {
"total": 702.6533558299859,
"count": 90937,
"self": 702.6533558299859
}
}
},
"workers": {
"total": 1.3499588920479368,
"count": 90937,
"self": 0.0,
"children": {
"worker_root": {
"total": 2227.593319506962,
"count": 90937,
"is_parallel": true,
"self": 1069.5588724749666,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.00539955699997563,
"count": 1,
"is_parallel": true,
"self": 0.0037828960000183542,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0016166609999572756,
"count": 10,
"is_parallel": true,
"self": 0.0016166609999572756
}
}
},
"UnityEnvironment.step": {
"total": 0.07540793000003987,
"count": 1,
"is_parallel": true,
"self": 0.0005589650000388247,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0003846160000193777,
"count": 1,
"is_parallel": true,
"self": 0.0003846160000193777
},
"communicator.exchange": {
"total": 0.07211972400000377,
"count": 1,
"is_parallel": true,
"self": 0.07211972400000377
},
"steps_from_proto": {
"total": 0.0023446249999778956,
"count": 1,
"is_parallel": true,
"self": 0.000789874999895801,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015547500000820946,
"count": 10,
"is_parallel": true,
"self": 0.0015547500000820946
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1158.0344470319953,
"count": 90936,
"is_parallel": true,
"self": 46.82910365792782,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 25.211666107026588,
"count": 90936,
"is_parallel": true,
"self": 25.211666107026588
},
"communicator.exchange": {
"total": 936.3654902629801,
"count": 90936,
"is_parallel": true,
"self": 936.3654902629801
},
"steps_from_proto": {
"total": 149.62818700406103,
"count": 90936,
"is_parallel": true,
"self": 29.31301810904256,
"children": {
"_process_rank_one_or_two_observation": {
"total": 120.31516889501847,
"count": 909360,
"is_parallel": true,
"self": 120.31516889501847
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00021376399990913342,
"count": 1,
"self": 0.00021376399990913342,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 2203.7704966491942,
"count": 2146980,
"is_parallel": true,
"self": 51.288569401228415,
"children": {
"process_trajectory": {
"total": 1344.9229527639682,
"count": 2146980,
"is_parallel": true,
"self": 1342.8973949559677,
"children": {
"RLTrainer._checkpoint": {
"total": 2.0255578080004852,
"count": 10,
"is_parallel": true,
"self": 2.0255578080004852
}
}
},
"_update_policy": {
"total": 807.5589744839976,
"count": 454,
"is_parallel": true,
"self": 556.7220909789919,
"children": {
"TorchPPOOptimizer.update": {
"total": 250.83688350500574,
"count": 4540,
"is_parallel": true,
"self": 250.83688350500574
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.12593439900001613,
"count": 1,
"self": 0.0008786770004007849,
"children": {
"RLTrainer._checkpoint": {
"total": 0.12505572199961534,
"count": 1,
"self": 0.12505572199961534
}
}
}
}
}
}
}